INDEX

Explanations

actions related to clothing and adornment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

isor

-0.17

 fantasy

-0.17

zik

-0.16

ream

-0.15

Fant

-0.15

å¼Ĥ

-0.15

 scrape

-0.14

 defence

-0.14

\Mapping

-0.14

 Fantasy

-0.14

POSITIVE LOGITS

-loop

0.20

 loops

0.20

 loop

0.20

 Knot

0.18

 Loop

0.18

ãĤ¤ãĥ¤

0.17

_loop

0.17

 LOOP

0.16

loop

0.16

 knot

0.16

Activations Density 0.049%

actions related to clothing and adornment

No Comments

No Known Activations