INDEX

Explanations

words and concepts related to re-evaluation and reinterpretation

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

atten

-0.17

_flutter

-0.16

Ð¾Ð²Ð°ÑĢ

-0.15

 recovery

-0.15

uma

-0.14

leting

-0.14

trusted

-0.14

jal

-0.14

groupon

-0.14

recover

-0.14

POSITIVE LOGITS

 birth

0.18

0.17

elling

0.16

ÅĻeh

0.16

re

0.15

 context

0.15

 contextual

0.15

çĶŁ

0.14

Activations Density 0.030%

words and concepts related to re-evaluation and reinterpretation

No Comments

No Known Activations