INDEX

Explanations

references and citations in academic texts

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

ãĥ¼ãĥ¬

-0.15

 Shine

-0.15

Ã©ru

-0.14

ÏģÎ¿Ïħ

-0.14

elan

-0.14

anje

-0.14

letic

-0.14

=Value

-0.14

ampa

-0.14

POSITIVE LOGITS

Hol

0.16

acid

0.15

hol

0.15

AVOR

0.15

ACKET

0.14

anager

0.14

Ca

0.14

autor

0.13

irable

0.13

hol

0.13

Activations Density 0.008%

references and citations in academic texts

No Comments

No Known Activations