INDEX

Explanations

nouns related to specific food items and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ept

-0.17

 DISPATCH

-0.16

StackTrace

-0.15

rog

-0.15

rouw

-0.15

à¤¾:

-0.14

.getServer

-0.14

çĽĽ

-0.13

CHED

-0.13

UPER

-0.13

POSITIVE LOGITS

alice

0.15

burgh

0.14

ertz

0.14

hire

0.14

Lif

0.14

unami

0.13

idable

0.13

bor

0.13

 Relay

0.13

eric

0.13

Activations Density 0.597%

nouns related to specific food items and brands

No Comments

No Known Activations