INDEX

Explanations

various classifications, levels, types, or options in the context of items or concepts, often indicating differences or variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ugins

-0.16

_vs

-0.15

agli

-0.15

vs

-0.15

ueva

-0.15

ampler

-0.15

OLER

-0.14

nÃ©

-0.14

_HTTP

-0.14

antry

-0.14

POSITIVE LOGITS

yna

0.17

gre

0.17

orp

0.17

ardi

0.16

 depending

0.16

afa

0.16

aman

0.15

TECT

0.15

ynec

0.14

depending

0.14

Activations Density 0.456%

various classifications, levels, types, or options in the context of items or concepts, often indicating differences or variations

No Comments

No Known Activations