INDEX

Explanations

phrases and terms related to access and availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

oupon

-0.15

ati

-0.13

emon

-0.13

_typ

-0.13

_FAMILY

-0.13

daf

-0.13

 unsus

-0.13

 sana

-0.12

 Arcade

-0.12

udos

-0.12

POSITIVE LOGITS

 access

0.88

access

0.73

 Access

0.66

Access

0.65

 acess

0.64

_access

0.64

-access

0.63

 acces

0.63

.access

0.60

 accesses

0.60

Activations Density 0.242%

phrases and terms related to access and availability

No Comments

No Known Activations