INDEX

Explanations

references to programming structures and events in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Krist

-0.14

ibar

-0.14

jr

-0.14

-0.13

 Ø§Ùĥ

-0.13

_literals

-0.13

sizei

-0.13

pul

-0.13

olta

-0.13

POSITIVE LOGITS

ingen

0.15

idis

0.14

ity

0.14

ÑĢÑĮ

0.14

eshire

0.14

imeo

0.13

ãĥ¼ãĤ¯

0.13

iscard

0.13

hare

0.13

uali

0.13

Activations Density 0.059%

references to programming structures and events in code

No Comments

No Known Activations