INDEX

Explanations

factor

np_max-act · gemini-2.0-flash

The neuron activates on mentions of “transcription factor” (and its related abbreviations like TFs) in the text.

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

 karş

-0.07

-0.06

 youtube

-0.06

YLE

-0.06

irteen

-0.06

 pipe

-0.06

 flames

-0.06

loan

-0.06

 Pipe

-0.06

Pep

-0.06

POSITIVE LOGITS

 아니라

0.08

_SAMPLES

0.06

_aff

0.06

 factor

0.06

offers

0.06

 Factor

0.06

 بنابراین

0.06

 کمی

0.06

階

0.06

 فول

0.06

Activations Density 0.004%

factor

The neuron activates on mentions of “transcription factor” (and its related abbreviations like TFs) in the text.

No Comments

No Known Activations