INDEX

Explanations

references to unique or characteristic attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ender

-0.15

clc

-0.15

ÐŁÐļ

-0.15

/jav

-0.14

aklÄ±

-0.14

 Flame

-0.14

ow

-0.14

.createComponent

-0.14

onas

-0.14

 fisse

-0.13

POSITIVE LOGITS

uk

0.17

arna

0.14

agus

0.14

CADE

0.14

à¸§à¸ĩà¸¨

0.14

bor

0.13

âĢĮØªØ±ÛĮÙĨ

0.13

ylene

0.13

iber

0.13

Activations Density 0.003%

references to unique or characteristic attributes

No Comments

No Known Activations