INDEX

Explanations

references to spokespersons or representatives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rait

-0.15

erais

-0.15

ajo

-0.15

å¯Ħ

-0.15

anium

-0.15

hoa

-0.14

elig

-0.14

agus

-0.14

vent

-0.14

inois

-0.14

POSITIVE LOGITS

 adherence

0.16

OE

0.15

athy

0.15

oup

0.14

ed

0.14

Î½Îµ

0.14

INF

0.14

zie

0.14

athe

0.14

warts

0.14

Activations Density 0.010%

references to spokespersons or representatives in various contexts

No Comments

No Known Activations