INDEX

Explanations

rating and scoring systems related to games or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Pearce

-0.17

adden

-0.17

rement

-0.15

abo

-0.15

nez

-0.15

itz

-0.15

illes

-0.14

Asc

-0.14

nth

-0.14

POSITIVE LOGITS

possible

0.17

$max

0.17

MAX

0.17

 Rich

0.16

 maxi

0.16

ï¼ĳï¼Ĳ

0.16

imax

0.16

Max

0.16

 possible

0.15

yor

0.15

Activations Density 0.016%

rating and scoring systems related to games or products

No Comments

No Known Activations