INDEX

Explanations

mentions of specific entities or objects in various contexts, including locations and products

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

Ø´ÙĩØ±

-0.17

Erd

-0.15

ÑĢÐ¸Ð²Ð°

-0.15

ald

-0.14

rosse

-0.14

athi

-0.14

PLA

-0.13

 Trait

-0.13

enstein

-0.13

æı

-0.13

POSITIVE LOGITS

ovah

0.14

 Inhal

0.14

Editors

0.14

BAB

0.14

_magic

0.14

hints

0.14

allel

0.14

 bÃłi

0.13

ipe

0.13

Activations Density 0.670%

mentions of specific entities or objects in various contexts, including locations and products

No Comments

No Known Activations