INDEX

Explanations

elements describing height or elevation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ipse

-0.15

ROLL

-0.15

tgl

-0.15

 Alley

-0.15

 Ð²Ð¿

-0.15

ÙĪØ§

-0.14

roleum

-0.14

uddy

-0.14

æ±Ł

-0.14

razil

-0.14

POSITIVE LOGITS

ampaign

0.18

 heights

0.18

 above

0.18

above

0.17

-high

0.17

Above

0.16

 Above

0.16

 ceilings

0.16

-mounted

0.16

spy

0.16

Activations Density 0.312%

elements describing height or elevation

No Comments

No Known Activations