INDEX

Explanations

references to specific individuals and their professional roles or credentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 frag

-0.17

ãģŀ

-0.15

 Toronto

-0.15

çīĩ

-0.15

catalog

-0.14

 Governors

-0.14

phia

-0.14

Summary

-0.14

bib

-0.14

 Ã¼

-0.14

POSITIVE LOGITS

sports

0.20

 Local

0.19

 LOCAL

0.19

.RightToLeft

0.18

locals

0.18

 multimedia

0.18

 sports

0.18

@register

0.17

ometown

0.17

 local

0.17

Activations Density 0.156%

references to specific individuals and their professional roles or credentials

No Comments

No Known Activations