INDEX

Explanations

phrases related to recommendations and assessments of situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oldt

-0.16

UGH

-0.15

atten

-0.15

ugh

-0.15

tainment

-0.15

orton

-0.14

 Stocks

-0.14

aco

-0.14

uggy

-0.14

unya

-0.14

POSITIVE LOGITS

 preferred

0.24

preferred

0.22

 ideal

0.18

recommended

0.18

 recommended

0.18

 best

0.18

 needed

0.17

 appropriate

0.17

ideal

0.16

 optimal

0.16

Activations Density 0.156%

phrases related to recommendations and assessments of situations

No Comments

No Known Activations