INDEX

Explanations

phrases related to prominent issues or themes in discussions

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

Org

-0.16

anlÄ±

-0.16

 Malik

-0.16

org

-0.14

Haj

-0.14

ãĥ¼ãĥĦ

-0.14

 honeymoon

-0.13

 lonely

-0.13

 Bryan

-0.13

Rah

-0.13

POSITIVE LOGITS

abad

0.16

nda

0.16

ses

0.16

pery

0.15

heim

0.15

ocale

0.14

iry

0.14

ovu

0.14

ctl

0.14

odzi

0.14

Activations Density 0.413%

phrases related to prominent issues or themes in discussions

No Comments

No Known Activations