INDEX

Explanations

references to specific people, places, 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ano

-0.16

-0.15

Ð»Ð°Ð³Ð°

-0.15

 Sands

-0.15

unh

-0.15

/fixtures

-0.14

antee

-0.14

 Sing

-0.14

awi

-0.14

Ø¬ÙĪ

-0.14

POSITIVE LOGITS

eid

0.17

eut

0.16

ussen

0.15

avern

0.15

å·´

0.14

 BÃ¶l

0.14

hani

0.14

icum

0.14

ë°

0.14

 Dread

0.14

Activations Density 1.237%

references to specific people, places, and organizations

No Comments

No Known Activations