INDEX

Explanations

rhetorical questions and expressions of curiosity

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

Kis

-0.15

.mods

-0.15

iscopal

-0.15

 module

-0.15

 doch

-0.15

Ole

-0.14

ATALOG

-0.14

ctal

-0.13

jid

-0.13

Ð°Ð»Ð¾Ð¼

-0.13

POSITIVE LOGITS

0.16

0.15

Tut

0.14

ohon

0.14

Activations Density 0.125%

rhetorical questions and expressions of curiosity

No Comments

No Known Activations