INDEX

Explanations

terms related to social interactions and relationships within a community

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

agua

-0.15

UGIN

-0.15

atters

-0.15

hÃ¡

-0.14

agate

-0.14

ino

-0.14

hua

-0.14

hed

-0.13

unh

-0.13

apt

-0.13

POSITIVE LOGITS

esc

0.15

 involvement

0.14

ä¸įåı¯

0.14

ixo

0.14

rove

0.14

 Acres

0.14

elo

0.14

ŀ

0.14

ENCIL

0.14

Activations Density 0.004%

terms related to social interactions and relationships within a community

No Comments

No Known Activations