INDEX

Explanations

references to model identifiers or version numbers within technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð¾ÑĤÑĮ

-0.16

andin

-0.15

au

-0.14

spl

-0.14

anch

-0.14

ignet

-0.14

puter

-0.14

aci

-0.13

 Nack

-0.13

 Dave

-0.13

POSITIVE LOGITS

ioc

0.16

_ENT

0.14

ney

0.13

erguson

0.13

ayar

0.13

exter

0.13

oples

0.13

actory

0.13

Sas

0.13

Activations Density 0.012%

references to model identifiers or version numbers within technical documents

No Comments

No Known Activations