INDEX

Explanations

specific dates and numerical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãĥ³ãĤº

-0.14

Dt

-0.14

ously

-0.13

 Shelf

-0.13

inges

-0.13

 Programm

-0.13

yme

-0.13

bjerg

-0.13

brit

-0.13

mour

-0.13

POSITIVE LOGITS

izin

0.15

ension

0.14

Î³Î¿Î½

0.14

Ø³ØªØ±

0.14

enu

0.14

 twin

0.14

áº¿p

0.14

ABL

0.13

 jint

0.13

ë¶

0.13

Activations Density 0.038%

specific dates and numerical identifiers

No Comments

No Known Activations