INDEX

Explanations

phrases related to rules and boundaries within family and community contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 bÃło

-0.16

ÙĪÙĬØª

-0.14

 technical

-0.14

Technical

-0.14

ResourceId

-0.14

technical

-0.14

istÃ©

-0.14

ingu

-0.14

ogo

-0.14

POSITIVE LOGITS

 rules

0.24

 Rules

0.21

 parental

0.20

rules

0.20

Rules

0.19

 rule

0.19

_rules

0.19

 Monitoring

0.19

 enforcement

0.18

 enforce

0.18

Activations Density 0.066%

phrases related to rules and boundaries within family and community contexts

No Comments

No Known Activations