INDEX

Explanations

instances of the word "von" and related positional phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.25

ÙĩØ§ÛĮ

-0.16

ango

-0.15

 gord

-0.15

:;"

-0.14

illac

-0.14

Å¡li

-0.14

isas

-0.14

foon

-0.13

 omas

-0.13

POSITIVE LOGITS

 allem

0.16

ankind

0.16

èī²

0.14

.localization

0.14

_skb

0.14

ãģĵãģĿ

0.13

cret

0.13

osu

0.13

ailles

0.13

etro

0.13

Activations Density 0.017%

instances of the word "von" and related positional phrases

No Comments

No Known Activations