INDEX

Explanations

instances of speech or dialogue being referenced

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

pw

-0.17

_ms

-0.16

 fullest

-0.15

åĪ«

-0.15

 blot

-0.14

esson

-0.14

.ms

-0.14

cona

-0.14

aran

-0.14

POSITIVE LOGITS

linik

0.17

ADI

0.16

ãĥĬãĥ«

0.14

-Ð»Ð¸Ð±Ð¾

0.14

 ÙħØ«ÙĦØ§

0.13

Ø·Ùĩ

0.13

KeyId

0.13

ependency

0.13

 ÎĶÎ·

0.13

edException

0.13

Activations Density 0.043%

instances of speech or dialogue being referenced

No Comments

No Known Activations