INDEX

Explanations

elements related to film roles and performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

yonel

-0.17

usable

-0.16

atform

-0.15

utura

-0.15

aeda

-0.14

á»§i

-0.14

romise

-0.14

estination

-0.14

èŃĺ

-0.14

erable

-0.14

POSITIVE LOGITS

 role

0.80

 roles

0.75

role

0.66

 Role

0.64

-role

0.61

 Roles

0.60

Role

0.59

roles

0.56

 ROLE

0.54

Roles

0.54

Activations Density 0.108%

elements related to film roles and performances

No Comments

No Known Activations