INDEX

Explanations

phrases that indicate secrecy or hidden information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rastructure

-0.15

olist

-0.14

iland

-0.14

enty

-0.14

paramref

-0.14

.bp

-0.14

lixir

-0.13

ROI

-0.13

olie

-0.13

 stamp

-0.13

POSITIVE LOGITS

anth

0.15

igr

0.15

lingen

0.14

Ble

0.14

 Whites

0.13

interp

0.13

mdp

0.13

Ã©rc

0.13

Les

0.13

_abort

0.13

Activations Density 0.017%

phrases that indicate secrecy or hidden information

No Comments

No Known Activations