INDEX

Explanations

usage of common words and punctuation in casual dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã©rique

-0.16

DSL

-0.15

mination

-0.15

habi

-0.15

roach

-0.14

untu

-0.14

 Snyder

-0.14

rick

-0.14

peri

-0.14

roup

-0.14

POSITIVE LOGITS

quette

0.16

idal

0.15

UIL

0.14

 Buckingham

0.14

onga

0.13

ÙĪØ§Ø¬

0.13

 impress

0.13

rab

0.13

atura

0.13

Activations Density 0.000%

usage of common words and punctuation in casual dialogue

No Comments

No Known Activations