INDEX

Explanations

phrases indicating perception or observation of situations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ultipart

-0.16

oni

-0.16

LOSE

-0.15

ori

-0.15

onis

-0.14

 Fade

-0.14

yat

-0.14

 fact

-0.14

itor

-0.14

affen

-0.14

POSITIVE LOGITS

äºĨä¸Ģ

0.14

pyx

0.14

 Boulder

0.14

leck

0.14

cwd

0.13

ãĤīãģĽ

0.13

edeki

0.13

anst

0.13

pte

0.13

 differently

0.13

Activations Density 0.050%

phrases indicating perception or observation of situations or conditions

No Comments

No Known Activations