INDEX

Explanations

references to specific names and titles across various 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

éĤ¦

-0.16

âķĿ

-0.16

xit

-0.15

ibil

-0.15

sw

-0.15

ÑĨÐ¾Ð²

-0.14

reet

-0.14

arna

-0.14

hiba

-0.14

annels

-0.14

POSITIVE LOGITS

Tr

0.20

afil

0.16

(TR

0.15

&type

0.15

-Tr

0.14

Internet

0.14

orde

0.14

.TR

0.14

ahoma

0.14

(tr

0.14

Activations Density 0.039%

references to specific names and titles across various contexts

No Comments

No Known Activations