INDEX

Explanations

key phrases indicating significance or importance in a narrative

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

edException

-0.18

fu

-0.16

asser

-0.15

opes

-0.14

Advisor

-0.14

ãĥ¼ãĥ«ãĥī

-0.14

inen

-0.14

opensource

-0.14

Ã¦kke

-0.13

ca

-0.13

POSITIVE LOGITS

etr

0.17

 ÑģÐ°Ð¹ÑĤÑĸ

0.15

ë©

0.15

andes

0.15

atsby

0.14

ereg

0.14

ilha

0.14

.fs

0.14

etri

0.13

 Ð´ÐµÑĢÐ¶Ð°Ð²

0.13

Activations Density 0.206%

key phrases indicating significance or importance in a narrative

No Comments

No Known Activations