INDEX

Explanations

mentions of Monte Carlo, indicating a focus on this geographic location or related contexts

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

_DUMP

-0.15

 supers

-0.15

 Defense

-0.15

ÏĢÎ¿Ïį

-0.15

 TMPro

-0.15

Ð±Ñĸ

-0.14

_SEP

-0.14

Defense

-0.14

rong

-0.14

rin

-0.14

POSITIVE LOGITS

echa

0.17

ez

0.16

rette

0.16

egative

0.16

anos

0.14

ë¦½

0.14

ovich

0.14

Ã¼ven

0.14

urtles

0.14

ãĤ´ãĥª

0.14

Activations Density 0.013%

mentions of Monte Carlo, indicating a focus on this geographic location or related contexts

No Comments

No Known Activations