INDEX

Explanations

words related to geographical data and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aja

-0.14

ê·ł

-0.14

 perch

-0.14

lass

-0.14

ard

-0.14

ndl

-0.14

Ð¾ÑĢÐ¾Ð½

-0.13

 explicit

-0.13

 Pazar

-0.13

POSITIVE LOGITS

âĢİ

0.15

imary

0.15

 assorted

0.14

å±

0.14

atern

0.14

edo

0.13

ildo

0.13

angl

0.13

Ńå·ŀ

0.13

Activations Density 0.798%

words related to geographical data and conditions

No Comments

No Known Activations