INDEX

Explanations

key terms associated with rules, regulations, and conditions in 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.13

ÑĢÐ°ÑĤÐ½Ð¾

-0.13

anness

-0.13

 Uncategorized

-0.13

alary

-0.13

ÙģØ³

-0.13

Ð½Ð¸ÑĨÑĮ

-0.13

indy

-0.13

 situaci

-0.13

alles

-0.12

POSITIVE LOGITS

Ð¾ÐºÑĢÐµÐ¼Ð°

0.13

GORITH

0.13

 dabei

0.12

 wanna

0.12

 gotta

0.12

çĪ·

0.12

 unidentified

0.11

 legit

0.11

Ð²Ð°Ð¶Ð°

0.11

ï»¿#

0.11

Activations Density 0.009%

key terms associated with rules, regulations, and conditions in various contexts

No Comments

No Known Activations