INDEX

Explanations

words and phrases related to personal identity and social connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

iya

-0.15

 kraj

-0.15

kon

-0.15

emez

-0.14

Spo

-0.14

koc

-0.14

 comm

-0.14

 lÃ´

-0.14

Cle

-0.14

dik

-0.14

POSITIVE LOGITS

 ettÃ¤

0.16

aad

0.15

ellen

0.15

allon

0.15

gii

0.15

ksi

0.15

ELLOW

0.14

herits

0.14

 meille

0.14

aks

0.14

Activations Density 0.004%

words and phrases related to personal identity and social connections

No Comments

No Known Activations