INDEX

Explanations

references to a prominent central figure or main attraction in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

æľĹ

-0.17

TOTYPE

-0.16

apons

-0.15

rone

-0.15

Î³Î¿Ïħ

-0.15

ammers

-0.15

pts

-0.15

nal

-0.15

gabe

-0.15

İ

-0.15

POSITIVE LOGITS

0.15

PA

0.15

ar

0.14

onica

0.14

_PO

0.14

-hero

0.14

ziel

0.14

 loved

0.13

PA

0.13

 starred

0.13

Activations Density 0.032%

references to a prominent central figure or main attraction in various contexts

No Comments

No Known Activations