INDEX

Explanations

instances of phrases indicating transitions or connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 UNUSED

-0.14

iments

-0.14

IGO

-0.14

yor

-0.13

onda

-0.13

adium

-0.13

iesen

-0.13

rah

-0.13

rive

-0.13

essen

-0.13

POSITIVE LOGITS

dak

0.17

]={↵

0.17

BuilderFactory

0.16

ä½³

0.16

0.14

anz

0.14

ISCO

0.14

alc

0.13

(Photo

0.13

 Ú©ÙĦÛĮ

0.13

Activations Density 0.001%

instances of phrases indicating transitions or connections between ideas

No Comments

No Known Activations