INDEX

Explanations

references to various councils and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.synthetic

-0.16

cona

-0.16

 Suff

-0.16

ysi

-0.15

 Erotik

-0.15

HOLDER

-0.15

ÑĤÐµÑĢÐ¸

-0.14

.openg

-0.14

osti

-0.14

 tÃ½

-0.14

POSITIVE LOGITS

arter

0.14

Eld

0.14

chers

0.14

Pow

0.14

 Reflex

0.14

infer

0.14

HAM

0.13

 alien

0.13

 grav

0.13

cher

0.13

Activations Density 0.009%

references to various councils and organizations

No Comments

No Known Activations