INDEX

Explanations

since

np_max-act · gemini-2.0-flash

The neuron responds to the discourse marker “since.”

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

op

-0.09

ymbol

-0.08

berg

-0.07

ymbols

-0.07

OP

-0.07

apping

-0.07

app

-0.07

ap

-0.07

dop

-0.07

lop

-0.07

POSITIVE LOGITS

 since

0.11

 Since

0.11

Since

0.11

.Since

0.10

since

0.09

SN

0.08

 insecurity

0.08

_since

0.07

 sinc

0.07

Activations Density 0.032%

since

The neuron responds to the discourse marker “since.”

No Comments

No Known Activations