INDEX

Explanations

numerical data or statistics mentioned in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ols

-0.15

emoc

-0.15

OrElse

-0.14

ombs

-0.14

verity

-0.14

akin

-0.13

atk

-0.13

BootApplication

-0.13

units

-0.13

Ð°ÑĢÐ°Ð½

-0.13

POSITIVE LOGITS

å£

0.19

ium

0.17

 older

0.15

equ

0.15

rete

0.14

æ£

0.14

 Mist

0.14

ë£¨

0.13

Activations Density 0.001%

numerical data or statistics mentioned in a context

No Comments

No Known Activations