INDEX

Explanations

product specifications and packaging details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

mall

-0.15

rve

-0.13

vor

-0.13

anvas

-0.13

ESH

-0.13

 Cultural

-0.13

anova

-0.13

ãĤ¿ãĥ³

-0.13

agrant

-0.13

.Tr

-0.13

POSITIVE LOGITS

#ad

0.17

 pack

0.16

azen

0.16

 Leban

0.15

stants

0.15

elan

0.14

.Networking

0.14

pack

0.14

(pack

0.14

 Incontri

0.14

Activations Density 0.036%

product specifications and packaging details

No Comments

No Known Activations