INDEX

Explanations

terms related to classification and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

anya

-0.16

Ð±ÑĢÐ°

-0.16

ãĥ³ãĥĩãĤ£

-0.15

 yard

-0.15

enz

-0.15

sur

-0.15

 Frau

-0.14

inish

-0.14

recht

-0.14

endant

-0.14

POSITIVE LOGITS

arter

0.20

 espec

0.19

 spec

0.19

tax

0.18

arten

0.18

-tax

0.18

 species

0.17

_spinner

0.16

 arter

0.16

pecies

0.16

Activations Density 0.007%

terms related to classification and categorization

No Comments

No Known Activations