INDEX

Explanations

references to automotive parts and repair processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 lasers

-0.17

 laser

-0.16

LineStyle

-0.15

ybrid

-0.15

 Laser

-0.15

 tact

-0.15

scanner

-0.14

 vess

-0.14

adal

-0.14

Vic

-0.14

POSITIVE LOGITS

 provision

0.16

 cast

0.15

 lubric

0.15

dra

0.15

oggles

0.15

 manganese

0.15

_IMM

0.15

bak

0.14

 tropical

0.14

ãĥ

0.14

Activations Density 0.042%

references to automotive parts and repair processes

No Comments

No Known Activations