INDEX

Explanations

numerical data related to statistics and records in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

utters

-0.17

otti

-0.15

ires

-0.15

quit

-0.14

[^

-0.14

 Kear

-0.14

paque

-0.14

-0.13

andes

-0.13

éĩı

-0.13

POSITIVE LOGITS

_WAKE

0.15

ervo

0.15

iami

0.15

ascar

0.14

igid

0.14

Constructed

0.14

Coder

0.13

atsby

0.13

shima

0.13

finger

0.13

Activations Density 0.227%

numerical data related to statistics and records in various contexts

No Comments

No Known Activations