INDEX

Explanations

discussions involving comparisons and equivalences, especially in the context of sensitive societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ÑİÐ½

-0.16

sterol

-0.16

pector

-0.15

erves

-0.15

 muschi

-0.14

Dup

-0.14

ambre

-0.14

ician

-0.14

_cv

-0.13

 Fairfield

-0.13

POSITIVE LOGITS

rys

0.17

uby

0.15

initializer

0.15

 Gest

0.14

ãģ¡ãĤĩ

0.14

inet

0.14

à¸¤

0.13

æŁĦ

0.13

rit

0.13

Activations Density 0.150%

discussions involving comparisons and equivalences, especially in the context of sensitive societal issues

No Comments

No Known Activations