INDEX

Explanations

function definitions and related structure in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑĢÑĥÐº

-0.15

afil

-0.15

Î¾Î¹

-0.14

nze

-0.14

 defaultProps

-0.14

ault

-0.14

Produces

-0.13

ErrorMsg

-0.13

IsUnicode

-0.13

kovi

-0.13

POSITIVE LOGITS

*,

0.15

eken

0.14

ÅĻad

0.14

enton

0.14

{*}

0.14

agna

0.13

 Hayward

0.13

res

0.13

cest

0.13

Activations Density 0.154%

function definitions and related structure in code

No Comments

No Known Activations