INDEX

Explanations

specific identifiers or codes related to programming and database elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

afc

-0.14

odie

-0.14

 slack

-0.14

olini

-0.14

 Hubb

-0.14

HAM

-0.13

ammer

-0.13

è¼ª

-0.13

ead

-0.13

POSITIVE LOGITS

ÑĤÐ¸Ð¼

0.15

NIL

0.15

yna

0.14

ãĥĪãĥ«

0.14

ÑĢÐ¸ÑģÑĤÐ¸

0.14

THEN

0.13

PTR

0.13

Bry

0.13

quil

0.13

ãĥ¼ãĥĦ

0.13

Activations Density 0.029%

specific identifiers or codes related to programming and database elements

No Comments

No Known Activations