INDEX

Explanations

terms related to self-identity or self-employment concepts

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

umen

-0.15

lsi

-0.15

ãĥ©ãĤ¹

-0.14

Ø§ÙģØª

-0.14

enez

-0.14

 Pere

-0.14

ÙĪØ§Ø±

-0.14

aben

-0.13

çĮ®

-0.13

juan

-0.13

POSITIVE LOGITS

/self

0.24

ishly

0.23

same

0.23

(Self

0.22

-contained

0.21

 explanatory

0.21

ridge

0.20

lessly

0.20

Ã¤nd

0.20

 Portrait

0.20

Activations Density 0.024%

terms related to self-identity or self-employment concepts

No Comments

No Known Activations