INDEX

Explanations

internet forum discussions

np_max-act · gemini-2.0-flash

The neuron fires on common English content words—especially verbs (and some adjectives) that carry the main proposition of a sentence.

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

्ह

-0.07

 werd

-0.07

 pohled

-0.07

 vyrá

-0.07

ῖ

-0.06

UINT

-0.06

伍

-0.06

езульт

-0.06

 aver

-0.06

 substitute

-0.06

POSITIVE LOGITS

Nor

0.06

Summer

0.06

ociety

0.06

ERVER

0.06

Mp

0.06

.nn

0.06

 고객

0.06

'",↵

0.05

soup

0.05

useppe

0.05

Activations Density 0.039%

internet forum discussions

The neuron fires on common English content words—especially verbs (and some adjectives) that carry the main proposition of a sentence.

No Comments

No Known Activations