INDEX

Explanations

code-related terminology associated with debugging and graphics rendering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

bread

-0.15

imus

-0.14

oya

-0.14

wor

-0.14

 toast

-0.14

leaf

-0.14

Ð»Ð°

-0.14

uml

-0.14

 hver

-0.14

 pseud

-0.13

POSITIVE LOGITS

çį

0.18

alink

0.16

Ð¾Ð»Ñİ

0.15

anford

0.15

ebek

0.14

/plugins

0.14

itational

0.14

Äįet

0.14

 rencont

0.14

ÑģÑĤÐ¸Ð½

0.14

Activations Density 0.375%

code-related terminology associated with debugging and graphics rendering

No Comments

No Known Activations