INDEX

Explanations

references to swimming activities and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ed

-0.17

ahoma

-0.17

utton

-0.16

enting

-0.14

eval

-0.14

imonial

-0.13

ted

-0.13

Ã³ria

-0.13

POSITIVE LOGITS

ByExample

0.17

 Ð´Ð¾ÑĤ

0.15

|required

0.15

ç¿Ĵ

0.14

_ATOMIC

0.14

/photo

0.14

ende

0.14

éĵº

0.14

 cuda

0.14

ToObject

0.14

Activations Density 0.009%

references to swimming activities and related terms

No Comments

No Known Activations