INDEX

Explanations

references to personal experience and narrative storytelling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uka

-0.17

 round

-0.15

ushman

-0.15

ilo

-0.14

Ð»Ð°Ð¶

-0.14

bj

-0.14

á»ĳt

-0.14

POSITIVE LOGITS

Ð°ÑģÑģÐ¸Ð²

0.19

iba

0.17

/gpl

0.16

 experience

0.15

ãĥ«ãĤ¯

0.15

experience

0.15

ToProps

0.15

/Dk

0.14

oras

0.14

periences

0.14

Activations Density 0.109%

references to personal experience and narrative storytelling

No Comments

No Known Activations