INDEX

Explanations

legal references and citations

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

itung

-0.17

acier

-0.15

ÎºÎ¬

-0.15

çĿ

-0.14

evin

-0.14

umas

-0.14

att

-0.14

ingleton

-0.13

inas

-0.13

 Recorder

-0.13

POSITIVE LOGITS

eyen

0.16

fect

0.14

deniz

0.14

 navr

0.14

promo

0.14

eÃ§

0.14

UCT

0.14

uzzi

0.13

 DateTimeKind

0.13

Activations Density 0.010%

legal references and citations

No Comments

No Known Activations