INDEX

Explanations

references to occupations or roles held by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Wire

-0.15

serter

-0.15

ucer

-0.15

modele

-0.15

loyd

-0.14

ior

-0.14

oto

-0.14

tip

-0.14

SD

-0.14

reeze

-0.13

POSITIVE LOGITS

onda

0.18

essa

0.17

omit

0.16

 Campos

0.15

 Grimm

0.14

 fingerprints

0.14

aina

0.14

oram

0.13

ingerprint

0.13

é½

0.13

Activations Density 0.404%

references to occupations or roles held by individuals

No Comments

No Known Activations