INDEX

Explanations

names and titles related to various organizations, species, or medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

andin

-0.14

tok

-0.14

borough

-0.14

orie

-0.14

wyn

-0.13

ContextHolder

-0.13

 Mighty

-0.13

ãĥĥãĤ¯

-0.13

_URL

-0.13

tol

-0.13

POSITIVE LOGITS

Bow

0.17

 Rosenberg

0.15

egr

0.15

á»«ng

0.14

 CrossRef

0.14

 contempor

0.14

 Bris

0.14

Scr

0.14

estro

0.14

bow

0.13

Activations Density 0.060%

names and titles related to various organizations, species, or medical terms

No Comments

No Known Activations