INDEX

Explanations

programming constructs and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ipel

-0.16

SetColor

-0.15

akan

-0.15

cliffe

-0.14

æī¶

-0.13

StackSize

-0.13

uze

-0.13

foy

-0.13

à¸Ļà¸§

-0.13

standen

-0.13

POSITIVE LOGITS

cr

0.16

din

0.15

Maker

0.15

 idols

0.15

ESIS

0.15

é«ĺæ¸ħ

0.15

Din

0.14

 ************************************************************************

0.14

oris

0.14

one

0.14

Activations Density 0.020%

programming constructs and function definitions

No Comments

No Known Activations