INDEX

Explanations

groups or lists of items, updates, or categories in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ses

-0.17

[.

-0.16

ray

-0.14

 https

-0.14

 force

-0.14

__

-0.13

 commercials

-0.13

ÑģÐºÐ»Ð°Ð´

-0.13

POSITIVE LOGITS

ï¸

0.20

icus

0.17

URLException

0.17

_Lean

0.16

ideographic

0.15

WidthSpace

0.15

itÃ©s

0.15

ovÃ¡no

0.14

ascus

0.14

idades

0.14

Activations Density 0.228%

groups or lists of items, updates, or categories in a structured context

No Comments

No Known Activations