INDEX

Explanations

words related to the initiation of events or processes

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

anja

-0.16

Ã¼nchen

-0.15

ilter

-0.15

dub

-0.15

æĹ

-0.15

ancock

-0.15

ancia

-0.14

ssue

-0.14

 clad

-0.14

Cod

-0.14

POSITIVE LOGITS

 addCriterion

0.17

EUR

0.15

chy

0.15

holm

0.15

ieri

0.14

vais

0.14

 Wich

0.14

_ISO

0.14

 Ø¯Ùģ

0.14

chalk

0.13

Activations Density 0.067%

words related to the initiation of events or processes

No Comments

No Known Activations