INDEX

Explanations

phrases that indicate age or duration, particularly in relation to objects or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãĥŃãĥ¼

-0.17

Î¬Î½Î¹

-0.15

-0.14

Coy

-0.14

bs

-0.14

rud

-0.14

å²Ĺ

-0.13

gart

-0.13

 tslib

-0.13

 hooked

-0.13

POSITIVE LOGITS

 older

0.62

age

0.59

 aged

0.54

 oldest

0.53

 Older

0.51

 ages

0.49

old

0.47

-aged

0.46

older

0.46

Age

0.44

Activations Density 0.186%

phrases that indicate age or duration, particularly in relation to objects or systems

No Comments

No Known Activations