INDEX

Explanations

phrases and words related to names and personal identities in a specific language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

abel

-0.14

poÄį

-0.14

iga

-0.14

ire

-0.14

Works

-0.14

ayar

-0.13

awi

-0.13

Debe

-0.13

terraform

-0.13

Ã¡

-0.13

POSITIVE LOGITS

zell

0.16

orris

0.16

oola

0.16

 Fetch

0.15

 fetch

0.15

dera

0.15

Gor

0.14

 Neck

0.14

istar

0.14

rish

0.14

Activations Density 0.023%

phrases and words related to names and personal identities in a specific language

No Comments

No Known Activations