INDEX

Explanations

symbols and special characters

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

ÑģÐ»Ð¸

-0.15

ãģĹãĤĩ

-0.14

ramento

-0.14

 carrera

-0.13

rams

-0.13

abbo

-0.13

 Howell

-0.13

ç´ł

-0.13

ãĥ¥

-0.13

ilha

-0.13

POSITIVE LOGITS

odesk

0.16

¬¬

0.15

chner

0.15

ogie

0.15

[[[

0.14

oren

0.14

lfw

0.14

ladu

0.14

ober

0.14

RIX

0.14

Activations Density 0.005%

symbols and special characters

No Comments

No Known Activations