INDEX

Explanations

numerical information and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

agner

-0.18

anut

-0.17

lbrace

-0.16

qm

-0.15

atel

-0.15

quil

-0.15

iddi

-0.14

HEME

-0.14

lio

-0.14

lot

-0.14

POSITIVE LOGITS

iling

0.15

 Huss

0.15

aman

0.14

 weekly

0.14

no

0.14

 fortn

0.14

Sm

0.14

Pic

0.14

ram

0.14

 generally

0.14

Activations Density 0.019%

numerical information and dates

No Comments

No Known Activations