INDEX

Explanations

technical symbols and notation in written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

enas

-0.16

ÙĪØµ

-0.15

etes

-0.15

agua

-0.15

åĿ¡

-0.14

áº½

-0.14

oningen

-0.14

otte

-0.14

lope

-0.14

ignon

-0.14

POSITIVE LOGITS

 Carlson

0.16

laps

0.15

 Andres

0.14

--

0.14

-eslint

0.13

_Il

0.13

sed

0.13

Å¥

0.13

Activations Density 0.659%

technical symbols and notation in written content

No Comments

No Known Activations