INDEX

Explanations

references to acclaimed works or individuals in creative fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

cof

-0.15

 Clem

-0.14

ander

-0.14

trs

-0.14

 Guth

-0.14

asso

-0.14

akra

-0.14

eview

-0.13

ambda

-0.13

_pb

-0.13

POSITIVE LOGITS

unes

0.15

asi

0.15

 Ital

0.14

ised

0.14

right

0.14

ubar

0.14

 æ¿

0.14

itte

0.14

 literature

0.14

nt

0.13

Activations Density 0.004%

references to acclaimed works or individuals in creative fields

No Comments

No Known Activations