INDEX

Explanations

references to activities or concepts associated with organization, structuring, or preparation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shuttle

-0.15

ins

-0.15

-0.14

ÂĲ

-0.14

ille

-0.14

Ins

-0.14

 Jail

-0.14

stan

-0.14

POSITIVE LOGITS

aggi

0.16

 ninh

0.15

cci

0.15

ervals

0.15

swick

0.15

vero

0.15

Ä±sÄ±ndan

0.14

uki

0.14

chter

0.14

ECH

0.13

Activations Density 0.029%

references to activities or concepts associated with organization, structuring, or preparation

No Comments

No Known Activations