INDEX

Explanations

terms related to the judiciary and judicial processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ihan

-0.19

íķ

-0.14

udi

-0.14

utters

-0.14

_PTR

-0.14

bird

-0.13

IID

-0.13

 Ð½

-0.13

à¸Ńà¸ģ

-0.13

onse

-0.13

POSITIVE LOGITS

åº§

0.18

 Everett

0.17

 Decompiled

0.15

tat

0.14

tgt

0.14

aliz

0.14

hesive

0.14

 Geneva

0.14

 evacuated

0.14

UniformLocation

0.14

Activations Density 0.015%

terms related to the judiciary and judicial processes

No Comments

No Known Activations