INDEX

Explanations

references to programming languages and libraries, particularly related to Python and Docker

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iez

-0.16

zas

-0.16

Ã¨re

-0.15

ķ

-0.15

ting

-0.14

ongs

-0.14

Ã¨res

-0.14

ÏĥÎ¿

-0.14

ding

-0.14

thouse

-0.13

POSITIVE LOGITS

queda

0.15

segue

0.15

ãĥĭãĥĥãĤ¯

0.15

 Punch

0.15

/tiny

0.14

cube

0.14

sil

0.14

akens

0.14

seg

0.14

baugh

0.14

Activations Density 0.146%

references to programming languages and libraries, particularly related to Python and Docker

No Comments

No Known Activations