INDEX

Explanations

references to military or governmental organizations

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

Ð¶Ð¸

-0.16

OTS

-0.16

aldo

-0.15

misc

-0.15

urs

-0.14

ENSE

-0.14

åı°

-0.14

ours

-0.14

fy

-0.14

lea

-0.14

POSITIVE LOGITS

ÅĽ

0.16

vÃ¡l

0.15

 tong

0.14

ksen

0.14

ittest

0.14

ey

0.14

 Helm

0.14

/Base

0.14

kg

0.13

Activations Density 0.191%

references to military or governmental organizations

No Comments

No Known Activations