INDEX

Explanations

image dimensions and edition details of artwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

amilia

-0.16

 Leakage

-0.16

ologne

-0.14

esome

-0.14

 Seth

-0.13

å¢

-0.13

IP

-0.13

********************************************************************************

-0.13

EntryPoint

-0.13

 instant

-0.13

POSITIVE LOGITS

 anale

0.17

rette

0.15

asco

0.15

ãĥ¼ãĥĦ

0.15

Å¡ak

0.14

_CYCLE

0.14

POCH

0.14

_EXPR

0.14

aed

0.14

pite

0.14

Activations Density 0.012%

image dimensions and edition details of artwork

No Comments

No Known Activations