INDEX

Explanations

code-related structures and identifiers in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

igenous

-0.15

izzle

-0.15

.openapi

-0.15

 Weinstein

-0.14

azine

-0.14

asha

-0.14

 à¤īà¤ł

-0.14

Kl

-0.13

 Strange

-0.13

KL

-0.13

POSITIVE LOGITS

aeper

0.15

Î¯Î¸

0.15

0.14

 crossorigin

0.14

 Marr

0.14

ath

0.14

Î¼Î²

0.14

 cáº£

0.14

beb

0.14

Activations Density 0.001%

code-related structures and identifiers in programming or markup languages

No Comments

No Known Activations