INDEX

Explanations

quantifiable metrics and expressions of sentiments or tendencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

rego

-0.15

Tem

-0.14

ya

-0.14

lops

-0.14

uppen

-0.14

adÃŃ

-0.14

ëĬ¥

-0.14

luv

-0.13

á»¥y

-0.13

idar

-0.13

POSITIVE LOGITS

 towards

1.35

 toward

1.33

 Towards

1.08

Towards

1.07

Tow

0.97

 hacia

0.91

åĲĳ

0.86

owards

0.75

 verso

0.71

oward

0.69

Activations Density 0.469%

quantifiable metrics and expressions of sentiments or tendencies

No Comments

No Known Activations