INDEX

Explanations

references to digital platforms used for various purposes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

nesia

-0.15

closest

-0.14

 closest

-0.14

tte

-0.14

tax

-0.14

forgettable

-0.13

ÙħÙĩ

-0.13

Tax

-0.13

neas

-0.13

tax

-0.13

POSITIVE LOGITS

//{{

0.19

vider

0.15

-ie

0.15

ë¨¸

0.15

odore

0.15

insky

0.14

Äįe

0.14

rens

0.14

foy

0.14

åħµ

0.14

Activations Density 0.005%

references to digital platforms used for various purposes

No Comments

No Known Activations