INDEX

Explanations

mentions of the word "landed" and variations in the context of arrivals or achievements

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

ceries

-0.15

rug

-0.15

Roo

-0.14

owitz

-0.14

ici

-0.14

-auth

-0.14

 Humanities

-0.14

reet

-0.14

 Wide

-0.14

velle

-0.13

POSITIVE LOGITS

cxx

0.16

ÑĤÐ°Ð±

0.15

ãĥ©ãĤ¤ãĥĪ

0.14

linky

0.14

_legacy

0.14

rez

0.14

kker

0.13

 bore

0.13

tras

0.13

 scoop

0.13

Activations Density 0.004%

mentions of the word "landed" and variations in the context of arrivals or achievements

No Comments

No Known Activations