INDEX

Explanations

specific technical terms related to software or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ple

-0.16

Ple

-0.16

_kw

-0.16

ë²½

-0.15

AuthToken

-0.14

shr

-0.14

 authToken

-0.14

ÐĽÐĲ

-0.14

SystemService

-0.14

dna

-0.14

POSITIVE LOGITS

 Claims

0.26

 openid

0.25

 claims

0.25

 redirect

0.24

claims

0.23

 Discovery

0.23

Claims

0.23

 scopes

0.23

 issuer

0.22

OID

0.22

Activations Density 0.010%

specific technical terms related to software or programming concepts

No Comments

No Known Activations