INDEX

Explanations

specific references to events and experiences that involve significant actions or incidents

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

usercontent

-0.16

ainen

-0.16

Ã»t

-0.15

 nast

-0.14

borough

-0.14

 Silk

-0.14

 ç±³

-0.14

Umb

-0.14

 challenge

-0.13

eting

-0.13

POSITIVE LOGITS

ãģ°ãģĭãĤĬ

0.18

:selected

0.16

ITIES

0.16

otta

0.14

orca

0.14

ValueCollection

0.14

ë¦¬ì¹´

0.14

oleon

0.14

lus

0.14

avers

0.13

Activations Density 1.058%

specific references to events and experiences that involve significant actions or incidents

No Comments

No Known Activations