INDEX

Explanations

phrases indicating capability or potential

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

apple

-0.15

ãĥ¼ãĥł

-0.14

_behavior

-0.14

è±¡

-0.14

kins

-0.14

far

-0.14

 super

-0.14

stanov

-0.14

 Franco

-0.14

roupon

-0.14

POSITIVE LOGITS

 Wire

0.16

Bez

0.15

setFlash

0.15

kek

0.14

ieder

0.14

 tide

0.14

uren

0.14

inen

0.14

lendi

0.13

Activations Density 0.000%

phrases indicating capability or potential

No Comments

No Known Activations