INDEX

Explanations

and

np_max-act · gemini-2.0-flash

The neuron responds to the coordinating conjunction “and.”

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

 Kate

-0.07

ilet

-0.07

_voice

-0.07

Trad

-0.06

 range

-0.06

丰

-0.06

馆

-0.06

 pirate

-0.06

Eye

-0.06

.res

-0.06

POSITIVE LOGITS

ському

0.07

}});↵

0.07

 була

0.07

 Charset

0.06

(++

0.06

 controversial

0.06

 unload

0.06

kın

0.06

 Şubat

0.06

 та

0.06

Activations Density 0.243%

and

The neuron responds to the coordinating conjunction “and.”

No Comments

No Known Activations