INDEX

Explanations

programming-related elements, particularly in a syntax structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

viar

-0.15

ificate

-0.15

map

-0.14

 Crystal

-0.14

irting

-0.14

roller

-0.13

Ð½Ð°Ð´

-0.13

riting

-0.13

 Maiden

-0.13

 maps

-0.13

POSITIVE LOGITS

 PROCUREMENT

0.19

arts

0.15

ssa

0.14

_stderr

0.14

-Ñħ

0.14

rem

0.14

orus

0.14

oria

0.14

ball

0.14

balls

0.14

Activations Density 0.064%

programming-related elements, particularly in a syntax structure

No Comments

No Known Activations