INDEX

Explanations

instances of the word "scene" relating to events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ustos

-0.17

âĶĥ

-0.14

 Beled

-0.14

omatic

-0.14

.semantic

-0.14

ãĥ¥

-0.14

HDR

-0.13

aÄŁÄ±

-0.13

ÑīÑĸ

-0.13

Enumerator

-0.13

POSITIVE LOGITS

 cracked

0.14

 kuru

0.14

 EntityState

0.14

(concat

0.14

.lu

0.14

andan

0.14

boro

0.13

ikon

0.13

 dziaÅĤ

0.13

metatable

0.13

Activations Density 0.022%

instances of the word "scene" relating to events or situations

No Comments

No Known Activations