INDEX

Explanations

references to titles and terminology associated with films and literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

LEAR

-0.16

APH

-0.15

resa

-0.15

errs

-0.15

uen

-0.15

apia

-0.14

leur

-0.14

GINE

-0.14

iae

-0.14

 vypl

-0.14

POSITIVE LOGITS

 named

0.17

 same

0.17

 capitalized

0.16

 titled

0.16

 called

0.16

same

0.15

 similarly

0.15

åĲĮ

0.15

 mismo

0.15

overs

0.15

Activations Density 0.069%

references to titles and terminology associated with films and literature

No Comments

No Known Activations