INDEX

Explanations

mentions of hierarchical levels or classifications, particularly related to groups or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

sink

-0.15

ãĥ³ãĥĨãĤ£

-0.15

zn

-0.15

zin

-0.14

alm

-0.14

eric

-0.14

uality

-0.14

 ëĤ´ëł¤

-0.14

Ã¡nh

-0.14

inv

-0.14

POSITIVE LOGITS

most

0.25

-upper

0.17

dater

0.15

ipt

0.15

urtle

0.15

avage

0.14

halb

0.14

oles

0.14

hone

0.14

æ¬ł

0.14

Activations Density 0.017%

mentions of hierarchical levels or classifications, particularly related to groups or categories

No Comments

No Known Activations