INDEX

Explanations

references to recognition and fame 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ide

-0.16

_void

-0.15

erie

-0.15

eri

-0.14

-provider

-0.14

.ErrorCode

-0.14

orum

-0.14

 sources

-0.14

 Watkins

-0.13

 materials

-0.13

POSITIVE LOGITS

 recognition

0.17

 mainstream

0.17

ÄĻÅ¼

0.17

 popular

0.16

ienen

0.16

ledon

0.15

popular

0.15

KNOWN

0.15

Ã¶h

0.15

visibility

0.14

Activations Density 0.288%

references to recognition and fame in various contexts

No Comments

No Known Activations