INDEX

Explanations

phrases indicative of observation or awareness

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

 fact

-0.15

.ie

-0.15

VIEW

-0.14

Ø±ÙĬÙĥ

-0.14

atcher

-0.14

isi

-0.14

oret

-0.14

idend

-0.14

 experiences

-0.14

indr

-0.14

POSITIVE LOGITS

 evidence

0.25

 signs

0.25

 mention

0.21

 mentions

0.20

mention

0.18

 Evidence

0.18

 Signs

0.18

/he

0.18

 references

0.17

Evidence

0.17

Activations Density 0.198%

phrases indicative of observation or awareness

No Comments

No Known Activations