INDEX

Explanations

ent/tent

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the word “tentacle” (i.e. the “tent-” token in that context).

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

 birbir

-0.07

 Lover

-0.07

.attr

-0.07

 блю

-0.07

 translateY

-0.06

Destroy

-0.06

ickém

-0.06

SE

-0.06

POSITIVE LOGITS

 tent

0.15

 Tent

0.14

 tents

0.11

tent

0.10

 tentative

0.08

 camping

0.08

Oct

0.07

dit

0.07

October

0.07

 pět

0.07

Activations Density 0.003%

ent/tent

The neuron detects occurrences of the word “tentacle” (i.e. the “tent-” token in that context).

No Comments

No Known Activations