INDEX

Explanations

phrases indicating the presence of entities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãģ¡ãĤĥ

-0.15

ARSE

-0.14

amin

-0.14

auge

-0.14

ines

-0.14

Ð½Ð¸Ñĩ

-0.14

oretical

-0.13

il

-0.13

ÑĢÐ°Ñħ

-0.13

POSITIVE LOGITS

 sáºµn

0.16

ppo

0.14

abler

0.14

ppy

0.14

anj

0.14

itia

0.13

íĸ¥

0.13

á»Ł

0.13

oji

0.13

Activations Density 0.071%

phrases indicating the presence of entities or conditions

No Comments

No Known Activations