INDEX

Explanations

references to geographical locations and descriptions related to infrastructure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

edback

-0.16

hausen

-0.16

éĽ·

-0.15

 Ð¿ÑĢÐµÐ²ÑĭÑĪ

-0.14

ë¡ľëĤĺ

-0.14

Ð²ÐµÑģÑĤ

-0.14

Î¾Ïį

-0.14

ondheim

-0.13

)(__

-0.13

iks

-0.13

POSITIVE LOGITS

pci

0.17

hte

0.14

ptal

0.14

etic

0.14

ogo

0.14

0.13

gl

0.13

hton

0.13

alytics

0.13

SCO

0.13

Activations Density 1.308%

references to geographical locations and descriptions related to infrastructure

No Comments

No Known Activations