INDEX

Explanations

model

np_max-act · gemini-2.0-flash

This neuron detects mentions of “language model” (and related tokens like LM, LLM, Model, language, models) in technical explanations.

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

.appspot

-0.07

StatusCode

-0.07

 invocation

-0.06

背

-0.06

 вк

-0.06

.ast

-0.06

drFc

-0.06

$client

-0.06

vac

-0.06

 endowed

-0.06

POSITIVE LOGITS

 Tested

0.06

imeter

0.06

+B

0.06

 timezone

0.06

Ｍ

0.06

LINE

0.06

(...

0.06

infer

0.06

Φ

0.06

]("

0.06

Activations Density 0.010%

model

This neuron detects mentions of “language model” (and related tokens like LM, LLM, Model, language, models) in technical explanations.

No Comments

No Known Activations