INDEX

Explanations

mathematical expressions or equations

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

 Territories

-0.16

 vert

-0.14

ifo

-0.14

ÏĦÎ¿Î¹

-0.14

_None

-0.14

apor

-0.14

Stride

-0.14

ah

-0.13

nat

-0.13

POSITIVE LOGITS

den

0.16

tÃŃ

0.14

DDL

0.14

WARDED

0.14

ZE

0.14

 paci

0.14

rac

0.13

lar

0.13

IO

0.13

 Feld

0.13

Activations Density 0.094%

mathematical expressions or equations

No Comments

No Known Activations