INDEX

Explanations

specific references to software and programming languages or related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

izm

-0.15

itage

-0.14

 stem

-0.14

 Ritch

-0.14

 Masc

-0.14

 whip

-0.14

 role

-0.14

 Whip

-0.14

agal

-0.14

POSITIVE LOGITS

hari

0.19

eco

0.17

abox

0.17

opi

0.17

è¼

0.17

olatile

0.15

 crossorigin

0.15

omit

0.14

arya

0.14

Tier

0.14

Activations Density 0.298%

specific references to software and programming languages or related entities

No Comments

No Known Activations