INDEX

Explanations

abbreviations or acronyms related to organizations or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

umbn

-0.17

TEGER

-0.16

argon

-0.16

EFF

-0.15

atego

-0.15

RNA

-0.15

ipment

-0.15

prob

-0.14

AZY

-0.14

POSITIVE LOGITS

0.25

/OR

0.19

AS

0.17

asString

0.16

aaS

0.16

KEY

0.15

eko

0.15

0.14

ek

0.14

Activations Density 0.046%

abbreviations or acronyms related to organizations or initiatives

No Comments

No Known Activations