INDEX

Explanations

changes

np_max-act · gemini-2.0-flash

This neuron activates on mentions of “changes” (and related result‐reporting phrases) describing measured or observed alterations in scientific study contexts.

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

.policy

-0.07

PARATOR

-0.07

ΙΚΟ

-0.07

MESS

-0.06

 cheque

-0.06

 RestClient

-0.06

 bombs

-0.06

	sleep

-0.06

 SHORT

-0.06

repair

-0.06

POSITIVE LOGITS

 changes

0.07

â

0.07

abilece

0.06

 emerges

0.06

_cpp

0.06

 mutations

0.06

 běž

0.06

 Changes

0.06

 emerged

0.06

-strokes

0.06

Activations Density 0.040%

changes

This neuron activates on mentions of “changes” (and related result‐reporting phrases) describing measured or observed alterations in scientific study contexts.

No Comments

No Known Activations