INDEX

Explanations

references to familial relationships 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 @ 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

ober

-0.17

 damer

-0.16

gradable

-0.15

BoxLayout

-0.15

ucer

-0.14

istrovstvÃŃ

-0.14

ortho

-0.14

SetName

-0.14

ASCADE

-0.14

 recurs

-0.14

POSITIVE LOGITS

0.17

log

0.16

0.15

de

0.14

ipc

0.14

 store

0.14

 fist

0.14

 genitals

0.14

ãģĺ

0.14

 soft

0.14

Activations Density 0.089%

references to familial relationships and interactions

No Comments

No Known Activations