INDEX

Explanations

technical programming terms and function calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 impairment

-0.13

Ð»Ð°Ð´Ð°

-0.13

CLUDED

-0.12

ngen

-0.12

itol

-0.12

 pled

-0.12

Î¼Î¿

-0.12

--[[

-0.11

pedia

-0.11

Ðµ

-0.11

POSITIVE LOGITS

1.09

0.94

(@

0.84

(@

0.81

.@

0.76

,@

0.76

/@

0.74

@s

0.73

:@

0.73

=@

0.73

Activations Density 0.388%

technical programming terms and function calls

No Comments

No Known Activations