INDEX

Explanations

references to dips, both as food items and in various contexts, including viral or figurative uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

wf

-0.15

 mutual

-0.15

redd

-0.14

adan

-0.14

Ð¸

-0.13

ÙĩÙĩ

-0.13

lif

-0.13

emey

-0.13

 Hermes

-0.13

ate

-0.13

POSITIVE LOGITS

stick

0.15

gene

0.15

ensing

0.15

itous

0.15

latlong

0.14

 Besch

0.14

dip

0.14

Ä°T

0.14

 deepest

0.14

ering

0.14

Activations Density 0.038%

references to dips, both as food items and in various contexts, including viral or figurative uses

No Comments

No Known Activations