INDEX

Explanations

patterns of numerical sequences or time durations in song listings or track information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÄĻÅ¼

-0.16

ĶĦ

-0.15

ulus

-0.14

oku

-0.14

 tong

-0.14

UPLE

-0.13

éĢļãĤĬ

-0.13

 Morrow

-0.13

resse

-0.13

Archive

-0.13

POSITIVE LOGITS

addin

0.16

uria

0.15

_aspect

0.14

ÏģÎ¯

0.14

abstractmethod

0.14

izia

0.14

rios

0.14

.ManyToMany

0.13

Inline

0.13

 Chancellor

0.13

Activations Density 0.007%

patterns of numerical sequences or time durations in song listings or track information

No Comments

No Known Activations