INDEX

Explanations

words and phrases related to frequency and repetitive actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ozem

-0.16

oz

-0.15

oz

-0.14

 sanction

-0.14

bel

-0.14

bev

-0.14

Pry

-0.13

dll

-0.13

 Sasha

-0.13

ONGL

-0.13

POSITIVE LOGITS

Å¡lo

0.16

 inplace

0.15

queeze

0.15

lai

0.15

.LayoutStyle

0.14

enance

0.14

rÃ¥

0.14

æĹıèĩªæ²»

0.14

aina

0.14

.MM

0.14

Activations Density 0.018%

words and phrases related to frequency and repetitive actions or states

No Comments

No Known Activations