INDEX

Explanations

terms related to legal and regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

icari

-0.18

Spl

-0.16

 Sass

-0.16

Dup

-0.15

spl

-0.15

ekler

-0.15

ouden

-0.15

dob

-0.14

ross

-0.14

illet

-0.14

POSITIVE LOGITS

imum

0.15

 kepada

0.15

 Strip

0.15

inspace

0.15

inode

0.14

 onto

0.14

 æĸ¼

0.14

 Olson

0.14

æ·¡

0.14

 towards

0.14

Activations Density 0.251%

terms related to legal and regulatory contexts

No Comments

No Known Activations