INDEX

Explanations

words related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iaux

-0.17

arius

-0.16

recht

-0.15

ittings

-0.15

Law

-0.15

Law

-0.14

ty

-0.14

ersen

-0.14

POSITIVE LOGITS

Symbols

0.15

TOT

0.14

pike

0.14

iou

0.14

_RW

0.14

RCT

0.14

ÙĳØ§

0.14

à¤¿à¤«

0.14

 FontWeight

0.14

inja

0.14

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations