INDEX

Explanations

references to geographical proximity and location-based terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

_nsec

-0.16

ãĥ¬ãĥ³

-0.16

dden

-0.15

 Cáº§n

-0.15

 Naturally

-0.15

åºķ

-0.15

uen

-0.14

dbus

-0.14

anness

-0.14

POSITIVE LOGITS

0.16

ood

0.16

/close

0.15

chip

0.15

orte

0.14

-ever

0.14

oll

0.14

LETE

0.14

ilis

0.14

Activations Density 0.011%

references to geographical proximity and location-based terms

No Comments

No Known Activations