INDEX

Explanations

descriptions of social settings and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

stal

-0.16

ht

-0.15

 outgoing

-0.15

heim

-0.15

stad

-0.15

 Marg

-0.14

ply

-0.14

enberg

-0.14

ocrine

-0.14

 hills

-0.14

POSITIVE LOGITS

 inside

0.39

Inside

0.39

 Inside

0.38

inside

0.36

 indoors

0.33

 interior

0.32

_inside

0.30

 interiors

0.28

 indoor

0.28

åħ§

0.27

Activations Density 0.145%

descriptions of social settings and interactions

No Comments

No Known Activations