INDEX

Explanations

references to personal thoughts, feelings, and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ilog

-0.16

 reck

-0.15

 wondered

-0.15

suy

-0.14

duk

-0.14

VICE

-0.14

 wonder

-0.14

opus

-0.14

_try

-0.14

Ø¶Ø§

-0.14

POSITIVE LOGITS

 mentioned

0.24

 Mention

0.22

 mention

0.21

mentioned

0.21

 mentioning

0.21

mention

0.20

 disclaimer

0.18

 mentions

0.18

 touched

0.17

claimer

0.16

Activations Density 0.148%

references to personal thoughts, feelings, and experiences

No Comments

No Known Activations