INDEX

Explanations

references to geographic locations or descriptors of places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

umat

-0.16

prep

-0.15

-append

-0.15

áº©u

-0.15

ibo

-0.14

icl

-0.14

ilder

-0.14

è£ķ

-0.14

egas

-0.14

bite

-0.14

POSITIVE LOGITS

 Template

0.18

Template

0.18

dbo

0.17

Wik

0.16

 contents

0.16

CONTENT

0.16

Lua

0.16

 MainAxisAlignment

0.16

 Seal

0.16

pes

0.15

Activations Density 0.021%

references to geographic locations or descriptors of places

No Comments

No Known Activations