INDEX

Explanations

specific programming or coding syntax and elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elsen

-0.16

MUX

-0.15

ynn

-0.14

æİ§

-0.14

okud

-0.14

ocracy

-0.13

æŀĿ

-0.13

getDrawable

-0.13

 merely

-0.13

quam

-0.13

POSITIVE LOGITS

uled

0.15

yon

0.15

stalk

0.15

 McCabe

0.14

ierz

0.14

aining

0.14

 compens

0.14

 åĽ½å®¶

0.14

 compensated

0.14

ator

0.13

Activations Density 0.120%

specific programming or coding syntax and elements

No Comments

No Known Activations