INDEX

Explanations

legend

np_max-act · gemini-2.0-flash

The neuron fires on mentions of plot legends or colorbars (e.g. “legend,” “colorbar,” “bar”) in code or questions.

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

 agreement

-0.08

 agreements

-0.07

 Spend

-0.07

 Microsoft

-0.07

 Frequency

-0.07

.phone

-0.06

IDAD

-0.06

-ca

-0.06

jid

-0.06

'post

-0.06

POSITIVE LOGITS

ldc

0.07

 supplementary

0.06

영

0.06

щей

0.06

寸

0.06

@{$

0.06

elim

0.06

.hex

0.06

 standardUserDefaults

0.06

 ди

0.06

Activations Density 0.003%

legend

The neuron fires on mentions of plot legends or colorbars (e.g. “legend,” “colorbar,” “bar”) in code or questions.

No Comments

No Known Activations