INDEX

Explanations

instances of the word "beloved," indicating a focus on affection or cherished relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

itzer

-0.15

sla

-0.15

frauen

-0.14

 Ú¯ÙĪ

-0.14

TOTYPE

-0.14

ori

-0.14

Ã±

-0.14

ãĥ©ãĥĥãĤ¯

-0.14

ersiz

-0.14

-hook

-0.13

POSITIVE LOGITS

ably

0.19

ly

0.19

kind

0.16

/lo

0.16

ResponseStatus

0.16

å²

0.15

/h

0.15

hab

0.15

liness

0.14

liest

0.14

Activations Density 0.032%

instances of the word "beloved," indicating a focus on affection or cherished relationships

No Comments

No Known Activations