INDEX

Explanations

mutant/mutants

np_max-act · gemini-2.0-flash

This neuron fires on mentions of core experimental actions or findings—verbs like “encodes,” “identified,” “isolated,” and “mutants” that highlight gene cloning or mutant‐screening results.

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

escription

-0.06

แรง

-0.06

 Fiona

-0.06

 nejvyšší

-0.06

 barr

-0.06

Bur

-0.06

 leng

-0.06

<Option

-0.06

 생산

-0.06

かり

-0.06

POSITIVE LOGITS

[sub

0.06

!↵↵↵

0.06

mediate

0.06

:'',

0.06

PRS

0.06

 nghĩa

0.06

 uneven

0.06

’re

0.06

 augmented

0.06

*/
↵

0.06

Activations Density 0.009%

mutant/mutants

This neuron fires on mentions of core experimental actions or findings—verbs like “encodes,” “identified,” “isolated,” and “mutants” that highlight gene cloning or mutant‐screening results.

No Comments

No Known Activations

mutant/mutants

This neuron fires on mentions of core experimental actions or findings—verbs like “encodes,” “identified,” “isolated,” and “mutants” that highlight gene cloning or mutant‐screening results.

No Comments

No Known Activations