INDEX

Explanations

technical references and terms related to programming and web development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

fus

-0.16

-0.15

abar

-0.15

 Sabb

-0.15

uz

-0.15

-0.14

lio

-0.14

fir

-0.14

aned

-0.14

Ø§Øµ

-0.14

POSITIVE LOGITS

leta

0.16

ammad

0.15

rent

0.14

omm

0.14

jug

0.14

ROUT

0.14

Margins

0.14

Unnamed

0.14

 character

0.13

odus

0.13

Activations Density 0.002%

technical references and terms related to programming and web development

No Comments

No Known Activations