INDEX

Explanations

numerals and key identifiers in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ayout

-0.16

lobal

-0.15

opcode

-0.15

atri

-0.14

ov

-0.13

å¿µ

-0.13

enz

-0.13

anch

-0.13

×ķ

-0.13

ÙĪØ²

-0.13

POSITIVE LOGITS

ocs

0.17

antee

0.16

csi

0.15

hos

0.15

phe

0.14

yre

0.14

itus

0.14

onica

0.14

vs

0.14

hic

0.14

Activations Density 0.002%

numerals and key identifiers in technical contexts

No Comments

No Known Activations