INDEX

Explanations

references to interpersonal relationships and emotional dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olan

-0.16

otte

-0.15

Äĥng

-0.15

Ø¯Ø§Ø±

-0.15

orre

-0.15

 awaited

-0.15

iban

-0.14

enberg

-0.14

alle

-0.14

odash

-0.14

POSITIVE LOGITS

æķ¢

0.22

 risks

0.22

 risky

0.20

 bold

0.19

 risking

0.18

aud

0.18

 ÑĢÐ¸Ð·

0.17

-risk

0.17

ARAM

0.17

 risk

0.17

Activations Density 0.003%

references to interpersonal relationships and emotional dynamics

No Comments

No Known Activations