INDEX

Explanations

keywords related to political or organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

achel

-0.16

itre

-0.15

amon

-0.14

lei

-0.14

asonic

-0.14

kit

-0.14

itel

-0.14

 arreglo

-0.14

ib

-0.14

ing

-0.14

POSITIVE LOGITS

qed

0.16

_FILENO

0.15

æ±

0.15

getDrawable

0.15

_trampoline

0.15

anine

0.14

ieved

0.14

odyn

0.14

ertino

0.14

.AutoComplete

0.14

Activations Density 0.002%

keywords related to political or organizational contexts

No Comments

No Known Activations