INDEX

Explanations

specific nouns or identifiers related to various topics, potentially indicating important entities or concepts within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ubu

-0.18

 strtoupper

-0.15

.za

-0.14

POSIT

-0.14

anka

-0.14

umpt

-0.14

azz

-0.14

zyst

-0.14

Ĥ¨

-0.14

POSITIVE LOGITS

neau

0.18

åĭ

0.17

AFE

0.15

æľį

0.14

@brief

0.13

æº

0.13

ÏģÎ±ÏĤ

0.13

ãĥ¥

0.13

HasBeenSet

0.13

ideon

0.13

Activations Density 0.006%

specific nouns or identifiers related to various topics, potentially indicating important entities or concepts within the text

No Comments

No Known Activations