INDEX

Explanations

affiliations with professional organizations or societies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ç´Ķ

-0.17

ittel

-0.16

 Herz

-0.16

ypy

-0.16

addin

-0.15

bourg

-0.15

avigator

-0.15

urette

-0.15

uen

-0.14

 SYNC

-0.14

POSITIVE LOGITS

 recap

0.15

0.14

 Recap

0.14

edad

0.14

lays

0.14

YPES

0.14

.Chart

0.14

unt

0.14

 interconnected

0.14

 spit

0.13

Activations Density 0.044%

affiliations with professional organizations or societies

No Comments

No Known Activations