INDEX

Explanations

technical terms and concepts related to mathematics and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ologi

-0.16

 Gauge

-0.15

pps

-0.15

ÅŁt

-0.15

ORT

-0.15

egal

-0.14

/configuration

-0.14

ëĳ¥

-0.14

 Hath

-0.14

Lookup

-0.14

POSITIVE LOGITS

 graph

0.26

.Graph

0.22

0.21

graph

0.21

 intercept

0.20

 GRAPH

0.20

 graphs

0.20

-graph

0.19

_graph

0.19

Graph

0.19

Activations Density 0.066%

technical terms and concepts related to mathematics and programming

No Comments

No Known Activations