INDEX

Explanations

references to doctrines and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ISCO

-0.16

rip

-0.16

argas

-0.14

coli

-0.14

ÐµÐ¶

-0.14

fol

-0.14

hir

-0.14

saldo

-0.14

Sensitive

-0.14

fold

-0.13

POSITIVE LOGITS

odom

0.16

owl

0.16

 proven

0.16

ResponseBody

0.15

ezi

0.14

Ton

0.14

 Dickinson

0.14

Ton

0.14

SPATH

0.13

 vase

0.13

Activations Density 0.013%

references to doctrines and their descriptions

No Comments

No Known Activations