INDEX

Explanations

questions related to television shows and their statuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-lnd

-0.16

eyse

-0.15

iera

-0.14

_inches

-0.14

iese

-0.14

jong

-0.14

ÙĪÛĮØ³

-0.14

aty

-0.14

ied

-0.13

enticated

-0.13

POSITIVE LOGITS

uner

0.16

aci

0.14

 Leone

0.14

gar

0.14

acen

0.14

 abstract

0.14

Tot

0.14

unas

0.14

oct

0.13

à¹Ħ

0.13

Activations Density 0.009%

questions related to television shows and their statuses

No Comments

No Known Activations