INDEX

Explanations

technical terms and identifiers used in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ãĥ¼ãĥĵ

-0.15

borough

-0.15

bands

-0.15

 à¸¿

-0.15

Ð¼Ð¼

-0.15

 Tham

-0.15

Ð»ÑıÐ½

-0.14

oze

-0.14

oble

-0.14

 reim

-0.14

POSITIVE LOGITS

Heb

0.15

 Inst

0.14

PRS

0.14

vido

0.14

ladu

0.14

agne

0.14

PEC

0.13

inst

0.13

ãĥ¼ãĥł

0.13

Inst

0.13

Activations Density 0.021%

technical terms and identifiers used in programming

No Comments

No Known Activations