INDEX

Explanations

references to the programming language Java

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

emek

-0.16

ANTE

-0.16

olumn

-0.15

ationToken

-0.15

 Intercept

-0.15

pekt

-0.14

REP

-0.14

leck

-0.14

LU

-0.14

elf

-0.14

POSITIVE LOGITS

_Global

0.15

spe

0.15

arten

0.15

 ÙħØ§ÙĦ

0.15

-speaking

0.14

arter

0.14

(Global

0.14

stant

0.14

 gross

0.14

 POSSIBILITY

0.14

Activations Density 0.004%

references to the programming language Java

No Comments

No Known Activations