INDEX

Explanations

terms related to parasites

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

ettel

-0.18

ned

-0.16

 Burr

-0.15

icken

-0.15

ÑĤÐ°Ð»

-0.15

slaught

-0.14

ermen

-0.14

eder

-0.14

romÄĽ

-0.14

 press

-0.14

POSITIVE LOGITS

 Trad

0.17

aggio

0.17

ault

0.14

trad

0.14

-host

0.14

iller

0.14

hta

0.14

imon

0.14

laz

0.14

OnError

0.14

Activations Density 0.007%

terms related to parasites

No Comments

No Known Activations