INDEX

Explanations

Scientific research

np_max-act · gemini-2.0-flash

This neuron detects mentions of specific biochemical compounds or substances (e.g. drugs, peptides, hormones).

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

entin

-0.08

$,

-0.07

 Dudley

-0.07

 therapist

-0.07

 zpět

-0.06

 menos

-0.06

Hol

-0.06

 linguistic

-0.06

_exact

-0.06

POSITIVE LOGITS

uyện

0.07

keiten

0.06

Allows

0.06

 τόσο

0.06

rror

0.05

 borrower

0.05

echn

0.05

 случа

0.05

誤

0.05

γε

0.05

Activations Density 0.175%

Scientific research

This neuron detects mentions of specific biochemical compounds or substances (e.g. drugs, peptides, hormones).

No Comments

No Known Activations