INDEX

Explanations

terms related to mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

çī§

-0.16

zin

-0.15

inue

-0.15

ghi

-0.14

mass

-0.14

Indented

-0.14

osen

-0.14

auen

-0.13

afe

-0.13

ingle

-0.13

POSITIVE LOGITS

ä½

0.16

 TRACE

0.15

atik

0.15

ronics

0.14

agli

0.14

.connector

0.14

ptom

0.14

{.

0.14

 Frag

0.14

0.13

Activations Density 0.016%

terms related to mathematical symbols and notation

No Comments

No Known Activations