INDEX

Explanations

names of individuals, particularly those associated with scientific or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

xba

-0.16

xbb

-0.16

xDD

-0.15

xcd

-0.15

xbc

-0.14

xeb

-0.14

dde

-0.14

ë²Į

-0.14

åĽ

-0.14

wdx

-0.14

POSITIVE LOGITS

AF

0.72

MF

0.66

DF

0.65

HF

0.65

AF

0.65

LF

0.64

Af

0.63

af

0.63

BF

0.63

NF

0.63

Activations Density 0.621%

names of individuals, particularly those associated with scientific or medical contexts

No Comments

No Known Activations