INDEX

Explanations

mentions of geographical locations, particularly those starting with "North" or "East."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aliz

-0.16

lopen

-0.15

cken

-0.15

OpenHelper

-0.15

/kubernetes

-0.14

/twitter

-0.14

Ø³ØªØ§ÙĨ

-0.14

neck

-0.14

ehler

-0.14

ë¶ĢíĦ°

-0.14

POSITIVE LOGITS

lesi

0.15

aways

0.15

 Cond

0.15

 Sher

0.15

conds

0.15

me

0.15

combe

0.14

down

0.14

ants

0.14

ê¸°ìĿĺ

0.14

Activations Density 0.020%

mentions of geographical locations, particularly those starting with "North" or "East."

No Comments

No Known Activations