INDEX

Explanations

terms related to Git and version control systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

pread

-0.15

 PREF

-0.15

fv

-0.14

ÐµÑĢÐ¸Ð½

-0.14

INET

-0.14

reh

-0.14

bir

-0.14

åĨł

-0.14

 Mata

-0.14

OND

-0.14

POSITIVE LOGITS

itto

0.16

rolled

0.15

indre

0.14

ptest

0.14

.toCharArray

0.14

 onDataChange

0.14

ismic

0.14

ÑıÐ²

0.14

etto

0.14

Activations Density 0.025%

terms related to Git and version control systems

No Comments

No Known Activations