INDEX

Explanations

terms related to compliance and regulatory processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ELS

-0.16

esome

-0.15

ãĤ¨ãĥ«

-0.15

åĬ¡

-0.15

serter

-0.15

isan

-0.14

 Slee

-0.14

 Rash

-0.14

tuk

-0.14

Cle

-0.14

POSITIVE LOGITS

ayÄ±p

0.16

 Denis

0.16

APO

0.14

Mey

0.13

 à¤ļà¤°

0.13

upy

0.13

aed

0.13

tee

0.13

 risk

0.13

urd

0.13

Activations Density 0.037%

terms related to compliance and regulatory processes

No Comments

No Known Activations