INDEX

Explanations

symbols and characters, particularly those typically used in mathematical or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

iÃªu

-0.16

ouver

-0.15

azor

-0.15

hani

-0.14

.readAs

-0.14

 bench

-0.13

shaw

-0.13

Ø´Ùĩ

-0.13

 zdrav

-0.13

.drive

-0.13

POSITIVE LOGITS

 falling

0.18

 Falling

0.15

 fall

0.14

abi

0.14

 Lead

0.14

 Landing

0.14

 fell

0.14

fell

0.14

fall

0.13

Activations Density 0.007%

symbols and characters, particularly those typically used in mathematical or technical contexts

No Comments

No Known Activations