INDEX

Explanations

phrases related to evaluation and decision-making challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

semb

-0.15

 midpoint

-0.15

 odds

-0.15

ney

-0.14

 zwar

-0.14

Purple

-0.14

ONGL

-0.14

zeich

-0.13

ç¯

-0.13

POSITIVE LOGITS

Ware

0.15

ãĥ¼ãĥ

0.15

onet

0.15

 Ware

0.15

 Weather

0.14

atts

0.14

/problem

0.14

omer

0.14

hausen

0.14

ÙħØ§ÙĨÛĮ

0.14

Activations Density 0.316%

phrases related to evaluation and decision-making challenges

No Comments

No Known Activations