INDEX

Explanations

technical terminology and references related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ð»Ð°Ð´Ð¸

-0.15

izza

-0.14

Wonder

-0.14

ãĤ

-0.14

ÏĢÎ¹Ïĥ

-0.14

igham

-0.14

/apis

-0.13

alez

-0.13

SelectionMode

-0.13

(Vec

-0.13

POSITIVE LOGITS

bic

0.15

dek

0.14

binary

0.14

cmc

0.14

-binary

0.14

 binary

0.14

ãĥ«ãĥī

0.14

_ERRORS

0.13

wa

0.13

 Binary

0.13

Activations Density 0.707%

technical terminology and references related to programming and software development

No Comments

No Known Activations