INDEX

Explanations

various forms of the letter 'F' and related symbols indicating formatting or typesetting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ifar

-0.16

STRU

-0.15

SION

-0.15

 Affero

-0.15

clearfix

-0.15

-mÃªme

-0.14

EGIN

-0.14

monic

-0.14

afone

-0.14

tron

-0.14

POSITIVE LOGITS

0.17

ed

0.17

iÃªn

0.15

ir

0.14

er

0.14

<_

0.14

mps

0.14

_LOADED

0.14

es

0.14

Activations Density 0.099%

various forms of the letter 'F' and related symbols indicating formatting or typesetting

No Comments

No Known Activations