INDEX

Explanations

mentions of well-known figures or media releases, particularly related to films and television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

bil

-0.15

acas

-0.14

 æĳ

-0.14

ctype

-0.14

inds

-0.13

MV

-0.13

idity

-0.13

ÑĢÑĸÐ²

-0.13

anyak

-0.13

iny

-0.13

POSITIVE LOGITS

Ħĸ

0.15

-Regular

0.15

readcr

0.15

-ignore

0.14

afil

0.14

uess

0.14

idot

0.14

ÐŁÐļ

0.13

iaux

0.13

Ã¼ss

0.13

Activations Density 0.411%

mentions of well-known figures or media releases, particularly related to films and television

No Comments

No Known Activations