INDEX

Explanations

references to government entities and officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ader

-0.16

oot

-0.16

dre

-0.15

ice

-0.15

Aut

-0.14

 Markus

-0.14

aut

-0.14

ite

-0.14

aves

-0.14

POSITIVE LOGITS

ahoma

0.15

iedo

0.15

¹Ħ

0.14

Tam

0.14

IBC

0.14

 ëķ

0.14

á»¥c

0.14

firm

0.14

isposable

0.14

batim

0.14

Activations Density 0.098%

references to government entities and officials

No Comments

No Known Activations