INDEX

Explanations

instances of the word "a" or its alternatives

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

oplayer

-0.16

icc

-0.15

áº©m

-0.14

ustil

-0.14

ÑĥÐ´Ð°

-0.14

avel

-0.14

 SELF

-0.14

-fetch

-0.14

 reco

-0.13

illing

-0.13

POSITIVE LOGITS

erin

0.16

ponents

0.16

ectors

0.15

 sucker

0.15

ÐºÐµÑĤ

0.15

oland

0.15

æľĿ

0.14

ÐµÑĦ

0.14

ozor

0.14

OME

0.13

Activations Density 0.011%

instances of the word "a" or its alternatives

No Comments

No Known Activations