INDEX

Explanations

to

np_max-act · gemini-2.0-flash

instructions or guidelines related to linking and embedding content in digital formats.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron detects instructional link-embedding phrases, especially occurrences of “link to” (often in “To link to…” contexts).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Grid

-0.06

SpinBox

-0.06

HR

-0.06

_pair

-0.06

 Lease

-0.06

 embarrassed

-0.05

 Christ

-0.05

 دهد

-0.05

eneration

-0.05

POSITIVE LOGITS

-date

0.07

ış

0.07

:?

0.07

 radios

0.07

 courte

0.07

 pretrained

0.07

oader

0.06

MG

0.06

 buyer

0.06

 pound

0.06

Activations Density 0.002%

to

instructions or guidelines related to linking and embedding content in digital formats.

This neuron detects instructional link-embedding phrases, especially occurrences of “link to” (often in “To link to…” contexts).

No Comments

No Known Activations

to

instructions or guidelines related to linking and embedding content in digital formats.

This neuron detects instructional link-embedding phrases, especially occurrences of “link to” (often in “To link to…” contexts).

No Comments

No Known Activations