INDEX

Explanations

terms related to sentencing and rehabilitation in a judicial context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 infer

-0.16

uda

-0.15

asket

-0.14

.ms

-0.14

igen

-0.14

 nackt

-0.14

 clich

-0.14

edges

-0.14

kili

-0.14

POSITIVE LOGITS

rame

0.17

 punishments

0.16

éĿĴ

0.15

éĽ

0.14

ennon

0.14

allo

0.14

 punishment

0.14

UserCode

0.14

validators

0.14

alore

0.14

Activations Density 0.295%

terms related to sentencing and rehabilitation in a judicial context

No Comments

No Known Activations