INDEX

Explanations

numerical data or metrics in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ibi

-0.15

paque

-0.15

uffman

-0.14

inidad

-0.14

 Ø³Ø±Ø¯

-0.14

arker

-0.14

/Instruction

-0.14

POSITIVE LOGITS

Æł

0.16

plib

0.13

Lit

0.13

artz

0.13

ëŀ

0.13

Æ¡

0.13

noinspection

0.13

lac

0.13

SOR

0.13

 ëª

0.13

Activations Density 0.010%

numerical data or metrics in a structured format

No Comments

No Known Activations