INDEX

Explanations

references to time periods, particularly those indicating early stages or beginnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

odyn

-0.15

gii

-0.15

atum

-0.14

onya

-0.14

pii

-0.14

pdev

-0.14

Scoped

-0.14

etin

-0.14

zg

-0.14

ewidth

-0.14

POSITIVE LOGITS

 stages

0.18

ÙĤØ§Øª

0.15

anco

0.15

 Marino

0.15

-stage

0.15

ilst

0.15

 Motors

0.14

acter

0.14

zÄħ

0.14

lement

0.14

Activations Density 0.106%

references to time periods, particularly those indicating early stages or beginnings

No Comments

No Known Activations