INDEX

Explanations

metrics and statistics associated with performance and scoring

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Sutton

-0.15

ilon

-0.15

asin

-0.14

Siz

-0.14

sip

-0.14

ilion

-0.14

 Stefan

-0.14

POSITIVE LOGITS

 score

0.72

 scores

0.64

score

0.62

-score

0.60

 Score

0.60

_score

0.57

Score

0.57

.score

0.56

-sc

0.54

 Scores

0.53

Activations Density 0.098%

metrics and statistics associated with performance and scoring

No Comments

No Known Activations