INDEX

Explanations

titles of movies and their related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

emia

-0.16

rott

-0.15

esco

-0.15

 jsonResponse

-0.14

emie

-0.14

à¸¸à¸Ķ

-0.14

baum

-0.14

-0.13

 Lump

-0.13

EDIA

-0.13

POSITIVE LOGITS

olio

0.15

 shade

0.15

 cockpit

0.15

oly

0.15

WT

0.15

vel

0.14

eld

0.14

á»ĥ

0.14

 dispatch

0.14

oli

0.14

Activations Density 0.021%

titles of movies and their related elements

No Comments

No Known Activations