INDEX

Explanations

professional contexts

np_max-act · gemini-2.0-flash

This neuron detects special formatting tokens marking header or metadata boundaries (e.g. “<|start_header_id|>”).

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

_parm

-0.07

 paragraphs

-0.07

announce

-0.06

 policymakers

-0.06

Portable

-0.06

емо

-0.06

 histograms

-0.06

aes

-0.06

 피해

-0.06

 اخ

-0.06

POSITIVE LOGITS

 Want

0.07

 Memory

0.07

ندگی

0.07

-pay

0.07

(ID

0.06

akter

0.06

Mut

0.06

_static

0.06

 buna

0.06

TG

0.06

Activations Density 0.432%

professional contexts

This neuron detects special formatting tokens marking header or metadata boundaries (e.g. “<|start_header_id|>”).

No Comments

No Known Activations