INDEX

Explanations

references to processes related to decisions and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ghost

-0.13

ÏĥÏī

-0.13

lice

-0.13

AVED

-0.12

PRINTF

-0.12

igkeit

-0.12

ÙĪØ¹

-0.12

ltk

-0.12

Ã±ana

-0.12

PropertyValue

-0.12

POSITIVE LOGITS

 process

1.26

process

1.07

 Process

1.00

 processes

0.93

Process

0.90

 proces

0.89

-process

0.88

 processo

0.88

_process

0.85

è¿ĩç¨ĭ

0.84

Activations Density 0.436%

references to processes related to decisions and evaluations

No Comments

No Known Activations