INDEX

Explanations

references to specific characters and their relationships in films or TV shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

aste

-0.15

 Sist

-0.15

Ret

-0.14

uted

-0.14

ako

-0.14

ient

-0.14

hon

-0.14

 Vend

-0.14

ole

-0.13

POSITIVE LOGITS

ovny

0.18

_attached

0.16

_compat

0.16

itte

0.14

itable

0.14

iggs

0.14

orian

0.14

ãĤıãģŁãģĹ

0.14

ugin

0.14

ITTE

0.14

Activations Density 0.022%

references to specific characters and their relationships in films or TV shows

No Comments

No Known Activations