INDEX

Explanations

references to specific people and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

atches

-0.16

atch

-0.16

uto

-0.15

ÐĿÐĺ

-0.15

 Frontier

-0.15

 Honey

-0.14

 congestion

-0.14

hen

-0.14

 squat

-0.14

anik

-0.14

POSITIVE LOGITS

 Spartan

0.20

 Halo

0.20

UNS

0.17

_SP

0.17

.SP

0.16

SP

0.15

strand

0.15

(SP

0.15

SP

0.15

PMC

0.15

Activations Density 0.020%

references to specific people and their relationships

No Comments

No Known Activations