INDEX

Explanations

references to objects or terms related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ecta

-0.15

sian

-0.15

adge

-0.15

spot

-0.14

Inf

-0.14

æĺĮ

-0.14

Criteria

-0.14

imers

-0.14

 Criteria

-0.14

odata

-0.14

POSITIVE LOGITS

ierz

0.19

ocks

0.14

_tC

0.14

 Volk

0.14

.synthetic

0.14

åį°

0.14

 intptr

0.14

 Dien

0.13

 footing

0.13

 prescription

0.13

Activations Density 0.012%

references to objects or terms related to programming and data structures

No Comments

No Known Activations