INDEX

Explanations

references to sliding or slider-related concepts in code or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isa

-0.15

ahl

-0.14

Ã©d

-0.14

itura

-0.14

deg

-0.14

DBC

-0.14

ces

-0.13

mailto

-0.13

UTION

-0.13

builtin

-0.13

POSITIVE LOGITS

riers

0.17

ignon

0.15

tons

0.15

ullan

0.15

ajor

0.14

-upper

0.14

 IonicPage

0.14

ngle

0.14

tw

0.14

ewis

0.14

Activations Density 0.004%

references to sliding or slider-related concepts in code or technical contexts

No Comments

No Known Activations