INDEX

Explanations

transfer

np_max-act · gemini-2.0-flash

This neuron detects mentions of (photo‐)induced electron‐transfer processes and related charge‐transfer phenomena.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gridSize

-0.06

Lee

-0.06

 Bless

-0.06

 Luke

-0.06

Ｃ

-0.06

 žádné

-0.06

.buffer

-0.06

uracion

-0.06

snake

-0.06

 sleeve

-0.06

POSITIVE LOGITS

FORMAT

0.07

 سان

0.07

SED

0.06

*@

0.06

 нед

0.06

 promptly

0.06

 concent

0.06

-full

0.06

_CALLBACK

0.06

_LIB

0.06

Activations Density 0.005%

transfer

This neuron detects mentions of (photo‐)induced electron‐transfer processes and related charge‐transfer phenomena.

No Comments

No Known Activations