INDEX

Explanations

references to geographic locations and web domains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

¹Ħ

-0.17

stal

-0.17

CDATA

-0.15

-0.14

iere

-0.14

trieve

-0.14

iol

-0.14

isco

-0.14

ors

-0.14

erm

-0.14

POSITIVE LOGITS

ĵ

0.16

edla

0.15

dis

0.15

berman

0.14

isz

0.14

endas

0.14

ivant

0.14

ativity

0.14

abeth

0.14

Ã¤nde

0.14

Activations Density 0.004%

references to geographic locations and web domains

No Comments

No Known Activations