INDEX

Explanations

bracket

np_max-act · gemini-2.0-flash

The neuron detects LaTeX math display delimiters (e.g. the “\[” sequence).

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

 Streaming

-0.06

 transit

-0.06

iterr

-0.06

 Mbps

-0.06

anean

-0.06

 Operational

-0.06

fed

-0.06

 another

-0.06

 concerns

-0.06

 tbsp

-0.06

POSITIVE LOGITS

Amy

0.06

lín

0.06

EMAIL

0.06

.ManyToManyField

0.06

询

0.06

乃

0.06

mav

0.06

_LANGUAGE

0.06

мя

0.06

owa

0.06

Activations Density 0.001%

bracket

The neuron detects LaTeX math display delimiters (e.g. the “\[” sequence).

No Comments

No Known Activations

bracket

The neuron detects LaTeX math display delimiters (e.g. the “\[” sequence).

No Comments

No Known Activations