INDEX

Explanations

titles of television shows or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

raci

-0.15

=sys

-0.15

ivor

-0.15

elfare

-0.14

à¹īà¸²à¸«

-0.14

æĹ¥

-0.14

aged

-0.14

erosis

-0.14

Day

-0.13

day

-0.13

POSITIVE LOGITS

ET

0.17

ET

0.16

ÚĨÙĩ

0.15

rok

0.15

iones

0.14

ipi

0.14

ÐķÐ¢

0.14

arden

0.14

ory

0.14

Activations Density 0.046%

titles of television shows or movies

No Comments

No Known Activations