INDEX

Explanations

technical specifications and data formatting within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Paz

-0.17

abis

-0.16

ÐµÐ½ÑĮ

-0.16

AFX

-0.15

rez

-0.15

 Oswald

-0.15

kav

-0.15

gib

-0.15

andbox

-0.14

enity

-0.14

POSITIVE LOGITS

0.77

0.75

0.74

0.73

0.72

0.66

0.63

0.61

Activations Density 0.085%

technical specifications and data formatting within documents

No Comments

No Known Activations