INDEX

Explanations

elements and attributes related to programming functions and variables

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

TK

-0.15

 Moss

-0.14

amins

-0.14

acco

-0.13

ä¿

-0.13

-ing

-0.13

sim

-0.13

Ø§Øº

-0.13

apos

-0.13

utos

-0.13

POSITIVE LOGITS

 acknow

0.15

olas

0.15

Uvs

0.14

kest

0.14

_mE

0.14

ija

0.14

olu

0.14

ola

0.14

ÐµÐ´Ð¸Ð½Ð¸

0.14

Activations Density 0.182%

elements and attributes related to programming functions and variables

No Comments

No Known Activations