INDEX

Explanations

references to geographic or institutional identifiers, specifically "NC" followed by a number

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ugen

-0.18

ugs

-0.15

ono

-0.15

 Berger

-0.15

ington

-0.15

ette

-0.15

 descended

-0.15

trp

-0.15

bo

-0.14

POSITIVE LOGITS

abeth

0.17

áº¿n

0.16

sword

0.16

Gear

0.15

rypted

0.14

pls

0.14

 Swords

0.14

sage

0.14

sah

0.14

AllWindows

0.13

Activations Density 0.007%

references to geographic or institutional identifiers, specifically "NC" followed by a number

No Comments

No Known Activations