INDEX

Explanations

references to smoke and related imagery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

sons

-0.17

inux

-0.15

á»ĩ

-0.14

estre

-0.14

igli

-0.14

hyth

-0.14

rem

-0.14

ÎĻÎĽ

-0.14

chaft

-0.13

iyas

-0.13

POSITIVE LOGITS

inkel

0.16

erp

0.15

lok

0.15

Sok

0.15

 dope

0.14

iness

0.14

-urlencoded

0.14

 Ð´Ñĥ

0.13

 Bent

0.13

Ð¡Ðł

0.13

Activations Density 0.011%

references to smoke and related imagery

No Comments

No Known Activations