INDEX

Explanations

occurrences of the word "Himalayan" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð°ÑĢÐ¾Ð²

-0.15

divider

-0.14

olar

-0.14

 aberr

-0.14

ãĥ¡ãĥ³ãĥĪ

-0.14

à¸Ńà¸ĩà¸Īà¸²à¸ģ

-0.14

ÑıÐ·

-0.14

.useState

-0.14

udoku

-0.14

ãĥ¥

-0.13

POSITIVE LOGITS

uti

0.17

anova

0.15

 Micha

0.15

oes

0.15

uta

0.15

nier

0.15

ED

0.14

orch

0.14

aded

0.14

agua

0.14

Activations Density 0.037%

occurrences of the word "Himalayan" and its variations

No Comments

No Known Activations