INDEX

Explanations

‐

np_max-act · gemini-2.0-flash

This neuron activates on the special (non-ASCII) hyphen/dash character (e.g. “‐”) used in hyphenated words and phrases.

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

sense

-0.07

()">

-0.07

 villages

-0.07

()
↵
↵
↵

-0.07

ke

-0.07

 недели

-0.07

VERRIDE

-0.06

)))↵

-0.06

POSITIVE LOGITS

‐

0.08

_exe

0.07

-ac

0.07

bindParam

0.07

gio

0.07

entimes

0.06

 JAXB

0.06

 Coil

0.06

 tape

0.06

$PostalCodesNL

0.06

Activations Density 0.002%

‐

This neuron activates on the special (non-ASCII) hyphen/dash character (e.g. “‐”) used in hyphenated words and phrases.

No Comments

No Known Activations