INDEX

Explanations

references to genealogical connections or family trees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

uo

-0.17

romo

-0.15

ampo

-0.15

iple

-0.14

qx

-0.14

ATED

-0.14

kening

-0.14

orsi

-0.14

kir

-0.13

iyat

-0.13

POSITIVE LOGITS

Dy

0.15

Ass

0.14

 evet

0.14

antal

0.14

ntax

0.14

activex

0.13

ouns

0.13

 ngá»«ng

0.13

ÐĲÑĢÑħÑĸÐ²

0.13

à¸¤

0.13

Activations Density 0.006%

references to genealogical connections or family trees

No Comments

No Known Activations