INDEX

Explanations

references to names or identifiers related to authors and studies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

abeth

-0.17

erable

-0.16

rick

-0.15

terra

-0.15

SingleOrDefault

-0.15

ãĥ¼ãĥį

-0.14

ulumi

-0.14

afone

-0.14

ighet

-0.14

azon

-0.14

POSITIVE LOGITS

ow

0.16

ien

0.15

axon

0.14

SSF

0.14

ift

0.13

utra

0.13

aklÄ±

0.13

nev

0.13

iÃª

0.13

Gow

0.13

Activations Density 0.231%

references to names or identifiers related to authors and studies

No Comments

No Known Activations