INDEX

Explanations

inquiries about technical processes and requests for help or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

dsl

-0.15

 Tile

-0.14

otor

-0.14

áº¡t

-0.14

quo

-0.14

 Orientation

-0.14

 current

-0.14

nar

-0.13

 Tent

-0.13

POSITIVE LOGITS

/cgi

0.17

owler

0.15

_vlog

0.15

tes

0.15

maz

0.14

EmptyEntries

0.14

Î¼Î¯

0.14

éĶ¦

0.14

rieb

0.14

.codes

0.14

Activations Density 0.287%

inquiries about technical processes and requests for help or clarification

No Comments

No Known Activations