INDEX

Explanations

quantities and descriptions related to experiences or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

vet

-0.15

-regexp

-0.15

ophobic

-0.14

olen

-0.14

TC

-0.13

apy

-0.13

à¥Įà¤²

-0.13

gee

-0.13

 materi

-0.13

POSITIVE LOGITS

few

0.32

 couple

0.25

few

0.24

Few

0.23

 little

0.23

lot

0.20

 nice

0.20

Few

0.20

bit

0.20

ouple

0.19

Activations Density 0.431%

quantities and descriptions related to experiences or items

No Comments

No Known Activations