INDEX

Explanations

sections and references within a scientific paper

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rix

-0.15

thers

-0.14

 KrÃ¡l

-0.14

Ð¾Ð´Ð°Ð²

-0.14

Ø¯Ø§Ø´Øª

-0.14

çĽĳåĲ¬é¡µéĿ¢

-0.14

YW

-0.14

Äįit

-0.14

 separators

-0.14

 ÙĨØ³Ø®Ùĩ

-0.14

POSITIVE LOGITS

.fun

0.15

 impost

0.14

 ambiance

0.14

yang

0.14

fans

0.14

lesai

0.13

 Vale

0.13

CKER

0.13

Activations Density 0.020%

sections and references within a scientific paper

No Comments

No Known Activations