INDEX

Explanations

attributes related to negative character traits or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Å±

-0.15

amic

-0.15

phan

-0.14

rey

-0.14

rego

-0.13

Ã¤nd

-0.13

raya

-0.13

ãĤ¹ãĤ¿ãĥ¼

-0.13

à¸²à¸°

-0.13

.addField

-0.13

POSITIVE LOGITS

TOOLS

0.15

ariant

0.15

0.14

/MPL

0.14

 Coul

0.13

æĥħ

0.13

 CONTRIBUTORS

0.13

çħ§

0.13

 YYSTYPE

0.13

dal

0.13

Activations Density 0.781%

attributes related to negative character traits or experiences

No Comments

No Known Activations