INDEX

Explanations

phrases expressing outcomes or results of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chts

-0.17

raÅ¾

-0.16

semb

-0.15

ombok

-0.15

_BITMAP

-0.15

monkey

-0.15

ãĥ¼ãĥĬ

-0.15

apon

-0.14

izu

-0.14

Ð½Ð°ÑĢ

-0.14

POSITIVE LOGITS

 pedest

0.16

Õ¡

0.16

FK

0.13

beck

0.13

AA

0.13

rites

0.13

Hum

0.13

nem

0.13

 Gain

0.12

Activations Density 0.166%

phrases expressing outcomes or results of actions

No Comments

No Known Activations