INDEX

Explanations

references to previous content or standards not being met

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anoi

-0.15

NSNotificationCenter

-0.15

alker

-0.15

anela

-0.15

ertino

-0.15

aco

-0.15

atcher

-0.14

nio

-0.14

burgh

-0.14

alk

-0.14

POSITIVE LOGITS

ries

0.15

 scarc

0.15

ë¦½

0.15

lam

0.15

ãĥĮ

0.14

rides

0.14

ior

0.14

OID

0.14

cale

0.14

jun

0.14

Activations Density 0.014%

references to previous content or standards not being met

No Comments

No Known Activations